{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H3MNWF6CGRS353MWEHWKSJ7TY6","short_pith_number":"pith:H3MNWF6C","schema_version":"1.0","canonical_sha256":"3ed8db17c23465beed9621eca927f3c78224aa45d6ddd45f118cf358c38dfd80","source":{"kind":"arxiv","id":"2308.07251","version":1},"attestation_state":"computed","paper":{"title":"Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Andrew S. Kayser, Cathy J. Price, Ioannis Pappas, John Ashburner, Liam Chalcroft, Mark D'Esposito, Mikael Brudfors, Ruben Louren\\c{c}o Pereira","submitted_at":"2023-08-14T16:38:13Z","abstract_excerpt":"Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range interactions in 3D brain lesion segmentation, we propose an all-convolutional transformer block variant of the U-Net architecture. We demonstrate that our model provides the greatest compromise in three factors: performance competitive with the state-of-the-art; parameter efficiency of a CNN; and the favourable inductive biases of a transformer. Our public imple"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.07251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-08-14T16:38:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e63cbbe6e4a23beddf07d6592cced0481a36f3dbc2774155d0b64b9f45c20b70","abstract_canon_sha256":"082ffc24512a360068eaae18ab1eb69da321e7b4cbd250bdc5d47f734ebd7fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:58.023686Z","signature_b64":"vt68w4EvBV6+4+WargXHmquMqA+BJNT8nX+9OSwz6w5xYPCHIVgIpZGpT+ELbD5zkamDJaSC25PCZgIGfMXJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed8db17c23465beed9621eca927f3c78224aa45d6ddd45f118cf358c38dfd80","last_reissued_at":"2026-07-05T06:40:58.023267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:58.023267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Andrew S. Kayser, Cathy J. Price, Ioannis Pappas, John Ashburner, Liam Chalcroft, Mark D'Esposito, Mikael Brudfors, Ruben Louren\\c{c}o Pereira","submitted_at":"2023-08-14T16:38:13Z","abstract_excerpt":"Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range interactions in 3D brain lesion segmentation, we propose an all-convolutional transformer block variant of the U-Net architecture. We demonstrate that our model provides the greatest compromise in three factors: performance competitive with the state-of-the-art; parameter efficiency of a CNN; and the favourable inductive biases of a transformer. Our public imple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07251","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.07251/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.07251","created_at":"2026-07-05T06:40:58.023321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07251v1","created_at":"2026-07-05T06:40:58.023321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07251","created_at":"2026-07-05T06:40:58.023321+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3MNWF6CGRS3","created_at":"2026-07-05T06:40:58.023321+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3MNWF6CGRS353MW","created_at":"2026-07-05T06:40:58.023321+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3MNWF6C","created_at":"2026-07-05T06:40:58.023321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12057","citing_title":"Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6","json":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6.json","graph_json":"https://pith.science/api/pith-number/H3MNWF6CGRS353MWEHWKSJ7TY6/graph.json","events_json":"https://pith.science/api/pith-number/H3MNWF6CGRS353MWEHWKSJ7TY6/events.json","paper":"https://pith.science/paper/H3MNWF6C"},"agent_actions":{"view_html":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6","download_json":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6.json","view_paper":"https://pith.science/paper/H3MNWF6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07251&json=true","fetch_graph":"https://pith.science/api/pith-number/H3MNWF6CGRS353MWEHWKSJ7TY6/graph.json","fetch_events":"https://pith.science/api/pith-number/H3MNWF6CGRS353MWEHWKSJ7TY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6/action/storage_attestation","attest_author":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6/action/author_attestation","sign_citation":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6/action/citation_signature","submit_replication":"https://pith.science/pith/H3MNWF6CGRS353MWEHWKSJ7TY6/action/replication_record"}},"created_at":"2026-07-05T06:40:58.023321+00:00","updated_at":"2026-07-05T06:40:58.023321+00:00"}